Leng Yueshuang, Wang Xiaoyi, Liao Weihua, Cao Ya
Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008; Molecular Imaging Center, Xiangya Hospital, Central South University, Changsha 410008, China.
Molecular Imaging Center, Xiangya Hospital, Central South University, Changsha 410008; Key Laboratory of Carcinogenesis and Invasion, Ministry of Education, Xiangya Hospital, Central South University, Changsha 410008; Cancer Research Institute, Xiangya School of Medicine, Central South University, Changsha 410078, China.
Zhong Nan Da Xue Xue Bao Yi Xue Ban. 2018 Apr 28;43(4):354-359. doi: 10.11817/j.issn.1672-7347.2018.04.004.
Gliomas are the most common brain primary tumors worldwide, which is the earliest sequenced cancer gene in the Cancer Genome Atlas (TCGA) project. The World Health Organization Classification Update of Central Nervous System (CNS) Tumors 2016 highlights that glioma is the first tumor classified based on both of the molecular markers and histology. Radiomics is an extraction approach for high-throughput data which collects the quantitative image information appearing. Combined imaging data with genomics and proteomics, radiomics show promising prediction for cancer diagnosis, treatment, and prognosis. In this review, the radiomic analysis methods applied in gliomas are highlighted. Some remarkable findings confirm the considerable potential of radiomics in clinical cancer research.
胶质瘤是全球最常见的脑原发性肿瘤，是癌症基因组图谱（TCGA）项目中最早进行测序的癌症基因。2016年世界卫生组织中枢神经系统（CNS）肿瘤分类更新强调，胶质瘤是首个基于分子标志物和组织学进行分类的肿瘤。放射组学是一种高通量数据提取方法，可收集出现的定量图像信息。将成像数据与基因组学和蛋白质组学相结合，放射组学在癌症诊断、治疗和预后方面显示出有前景的预测能力。在本综述中，重点介绍了应用于胶质瘤的放射组学分析方法。一些显著发现证实了放射组学在临床癌症研究中的巨大潜力。
